---
title: lightonai/Reason-ModernColBERT (Encode)
description: Reason-ModernColBERT is a late interaction model trained on the reasonir-hq dataset. It achieves extremely competitive performance on the BR. ModernBERT, 149M parameters.
canonical_url: https://superlinked.com/models/lightonai-reason-moderncolbert--encode
last_updated: 2026-05-24
---

# lightonai/Reason-ModernColBERT (Encode)

Reason-ModernColBERT is a late interaction model trained on the reasonir-hq dataset. It achieves extremely competitive performance on the BRIGHT benchmark aimed at evaluating reasoning-intensive retrieval performance, outperforming all existing models up to 7B (more than 45 times its size) and ev...

Source: [lightonai/Reason-ModernColBERT on HuggingFace](https://huggingface.co/lightonai/Reason-ModernColBERT)
Base model: [lightonai/GTE-ModernColBERT-v1](https://huggingface.co/lightonai/GTE-ModernColBERT-v1)

## Overview

| Field | Value |
|-------|-------|
| Architecture | ModernBERT |
| Parameters | 149M |
| Tasks | Encode, Score |
| Outputs | Multi-Vec |
| Dimensions | Multi-Vec: 128 |
| Max sequence length | 8,192 tokens |
| License | cc-by-nc-4.0 |
| Inputs | text |
| Languages | en |

## Benchmarks

### CQADupstackPhysicsRetrieval

Domain: scientific · Task: retrieval · Language: en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 · Queries: 1,039

**Quality:** ndcg at 10: 0.4382 · map at 10: 0.3824 · mrr at 10: 0.4397

**Performance (L4 b1 c16):** Corpus 29.6K tok/s · Corpus p50 61.0ms · Query 2.9K tok/s · Query p50 57.8ms

[Reference](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/)

### CosQA

Domain: technology · Task: retrieval · Language: en

Code search with natural language queries

Corpus: 6,267 · Queries: 500

**Quality:** ndcg at 10: 0.3443 · map at 10: 0.2641 · mrr at 10: 0.2620

**Performance (L4 b1 c16):** Corpus 12.7K tok/s · Corpus p50 60.8ms · Query 1.6K tok/s · Query p50 59.1ms

[Reference](https://arxiv.org/abs/2105.13239)

### FiQA2018

Domain: finance · Task: retrieval · Language: en

Financial opinion mining and question answering

Corpus: 57,599 · Queries: 648

**Quality:** ndcg at 10: 0.4081 · map at 10: 0.3315 · mrr at 10: 0.4936

**Performance (L4 b1 c16):** Corpus 30.7K tok/s · Corpus p50 71.5ms · Query 3.0K tok/s · Query p50 59.6ms

[Reference](https://sites.google.com/view/fiqa/)

### LegalBenchConsumerContractsQA

Domain: legal · Task: retrieval · Language: en

Question answering on consumer contracts

Corpus: 153 · Queries: 396

**Quality:** ndcg at 10: 0.7777 · map at 10: 0.7287 · mrr at 10: 0.7307

**Performance (L4 b1 c16):** Corpus 50.0K tok/s · Corpus p50 144.2ms · Query 4.2K tok/s · Query p50 60.7ms

[Reference](https://huggingface.co/datasets/nguha/legalbench)

### NFCorpus

Domain: medical · Task: retrieval · Language: en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 · Queries: 323

**Quality:** ndcg at 10: 0.3580 · map at 10: 0.1342 · mrr at 10: 0.5702

**Performance (L4 b1 c16):** Corpus 44.6K tok/s · Corpus p50 89.2ms · Query 1.4K tok/s · Query p50 56.3ms

[Reference](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/)

### SCIDOCS

Domain: scientific · Task: retrieval · Language: en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 · Queries: 1,000

**Quality:** ndcg at 10: 0.1710 · map at 10: 0.0986 · mrr at 10: 0.2991

**Performance (L4 b1 c16):** Corpus 27.0K tok/s · Corpus p50 80.8ms · Query 2.8K tok/s · Query p50 60.8ms

[Reference](https://allenai.org/data/scidocs)

### SciFact

Domain: scientific · Task: retrieval · Language: en

Scientific claim verification using research literature

Corpus: 5,183 · Queries: 300

**Quality:** ndcg at 10: 0.7380 · map at 10: 0.6953 · mrr at 10: 0.7076

**Performance (L4 b1 c16):** Corpus 41.6K tok/s · Corpus p50 83.7ms · Query 4.1K tok/s · Query p50 60.4ms

[Reference](https://github.com/allenai/scifact)

### StackOverflowQA

Domain: technology · Task: retrieval · Language: en

Programming question answering from Stack Overflow

Corpus: 19,931 · Queries: 1,994

**Quality:** ndcg at 10: 0.5934 · map at 10: 0.5591 · mrr at 10: 0.5591

**Performance (L4 b1 c16):** Corpus 35.4K tok/s · Corpus p50 84.4ms · Query 62.1K tok/s · Query p50 75.3ms

[Reference](https://arxiv.org/abs/2407.02883)